Bug-Bounty

ChatGPT HTML Preview XSS Enables Account Takeover

ATLAS OWASP HIGH ▲ 8.5 Simon Willison Nov 01, 2026

Researchers at Parameter Labs discovered a multi-stage exploit chain against ChatGPT's HTML preview (Canvas/artifacts) feature that allowed untrusted sandboxed iframe code to escape containment, inject unsandboxed iframes, and achieve JavaScript execution on the ChatGPT origin. By abusing a MathLive postMessage handler that used innerHTML and exploiting YouTube's oEmbed endpoint to bypass CSP script restrictions, attackers could exfiltrate private user data or perform actions on behalf of any signed-in user who visited a malicious shared ChatGPT URL. OpenAI patched the vulnerability and awarded a $5,000 bug bounty, though the severity of the exploit chain arguably warranted a higher payout.

OpenAI Compaction Flaw Exposes Hidden Reasoning in GPT-5.6

ATLAS OWASP HIGH ▲ 8.5 The Hacker News Oct 27, 2026

Security firm Xint discovered that OpenAI's compaction feature — which compresses long conversations into encrypted context items — could be manipulated to extract a reasoning model's hidden chain-of-thought as plain text. The technique bypassed protections OpenAI had shipped in August 2026 to prevent cross-model reasoning replay attacks, because compaction runs on the same model that generated the reasoning, circumventing the cross-model check. OpenAI confirmed and patched the vulnerability on October 23, 2026, awarding Xint a $6,000 bug bounty, though researchers warn that any server-side step reading decrypted reasoning while following user instructions remains a potential leakage vector.

Claude Used to Breach OpenAI Employee Account via Forum Flaw

ATLAS OWASP HIGH ▲ 8.2 Ars Technica Security Sep 19, 2026

Security researchers from Hacktron AI leveraged Anthropic's Claude to compromise an OpenAI employee's ChatGPT account through a vulnerability in OpenAI's Discourse-hosted community forum, gaining access to internal GitHub repositories. The attack chain — forum misconfiguration to internal SSO to privileged account — demonstrates how AI tooling can accelerate offensive security work against AI infrastructure. The incident also coincides with Anthropic disclosing that AI now leads 26% of its own R&D, raising broader concerns about recursive capability growth outpacing security controls.

Heap Overflow and SSO Flaw Let Hackers Access OpenAI Repos

ATLAS OWASP CRITICAL ▲ 8.5 OpenAI (via HN) Sep 18, 2026

Researchers from HacktronAI chained a heap buffer overflow in libheif (via ImageMagick on Discourse) with an OpenAI SSO misconfiguration to achieve RCE on community.openai.com, ultimately gaining access to employee ChatGPT and Codex accounts. With those compromised accounts, attackers could pivot to OpenAI's internal GitHub monorepo and connected services including Slack and email. The full exploit chain was discovered and disclosed responsibly within 72 hours, earning a $6,500 bug bounty.

Claude Opus Discovers API Flaw Enabling Ticket Fraud

ATLAS OWASP HIGH ▲ 8.2 Wired Security Jul 03, 2026

Security researcher Ian Carroll leveraged Anthropic's Claude Opus 4.7 to identify a critical vulnerability in Front Gate Tickets—a Live Nation subsidiary handling ticketing for major US festivals—that granted super-administrator access and the ability to freely issue tickets of any value. The case demonstrates LLM-assisted autonomous vulnerability discovery at scale, with Carroll noting the AI could likely have completed the full exploit chain without human intervention. Front Gate patched the flaw within 24 hours of disclosure, confirming no evidence of prior exploitation.

Claude Mythos Accelerates Automated Vulnerability Discovery

ATLAS OWASP MEDIUM ▲ 6.5 SecurityWeek Jun 10, 2026

Anthropic's Claude Mythos model is accelerating automated vulnerability discovery to a degree that may fundamentally disrupt the bug bounty and offensive security industries. As AI transitions from a force multiplier to a potential replacement for human security researchers, the economics and structure of vulnerability disclosure programs face significant pressure. The shift raises critical questions about the future of human-led offensive security and whether AI-generated findings will saturate or devalue traditional bounty programs.

Firefox Vulnerabilities Discovered via AI-Assisted Fuzzing

ATLAS OWASP HIGH ▲ 7.2 Simon Willison May 08, 2026

Mozilla used early access to Anthropic's Claude Mythos model to systematically discover and patch hundreds of previously unknown vulnerabilities in Firefox, including bugs over 15–20 years old. The effort demonstrates a step-change in AI-assisted vulnerability research, with April 2026 seeing 423 security fixes compared to a monthly baseline of 20–30. The same capability that empowered Mozilla's defenders also signals that adversaries with similar model access could industrialise exploit discovery against open-source software at scale.